Background And Purpose: The preoperative lymph node (LN) status is important for the treatment of colorectal cancer (CRC). Here, we established and validated a deep learning (DPL) model for predicting lymph node metastasis (LNM) in CRC.
Materials And Methods: A total of 423 CRC patients were divided into cohort 1 (training set, n = 238, testing set, n = 101) and cohort 2 (validation set, n = 84). Among them, 84 patients' tumour tissues were collected for RNA sequencing. The DPL features were extracted from enhanced venous-phase computed tomography of CRC using an autoencoder. A DPL model was constructed with the least absolute shrinkage and selection operator algorithm. Carcinoembryonic antigen and carbohydrate antigen 19-9 were incorporated into the DPL model to construct a combined model. The model performance was assessed by receiver operating characteristic curves, calibration curves and decision curves. The correlations between DPL features, which have been selected, and genes were analysed by Spearman' correlation, and the genes correlated with DPL features were used to transcriptomic analysis.
Results: The DPL model, integrated with 20 DPL features, showed a good discrimination performance in predicting the LNM, with areas under the curves (AUCs) of 0.79, 0.73 and 0.70 in the training set, testing set and validation set, respectively. The combined model had a better performance, with AUCs of 0.81, 0.77 and 0.73 in the three sets, respectively. Decision curve analysis confirmed the clinical application value of the DPL model and combined model. Furthermore, catabolic processes and immune-related pathways were identified and related with the selected DPL features.
Conclusion: This study presented a DPL model and a combined model for LNM prediction. We explored the potential genomic phenotypes related with DPL features. In addition, the model could potentially be utilized to facilitate the individualized prediction of LNM in CRC.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.radonc.2021.12.031 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Disruption of PCSK9 Suppresses Inflammation and Attenuates Abdominal Aortic Aneurysm Formation.
Arterioscler Thromb Vasc Biol
January 2025
State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Xicheng District, Beijing, China (Z.P., H.C., H.R., Z.G., Q.W., J.Y., Y.Z., M.W.).
Background: Abdominal aortic aneurysm (AAA) is a chronic vascular inflammatory disease without effective medications. PCSK9 (proprotein convertase subtilisin/kexin 9), a serine protease from the proprotein convertase family, has recently been associated with AAA in human genome-wide association studies. However, its role in AAA is unknown.
View Article and Find Full Text PDFMachine learning-driven assessment of heavy metal contamination in the impounded lakes of China's South-to-North Water Diversion Project: Identifying spatiotemporal patterns and ecological risks.
J Hazard Mater
December 2024
Institute of Hydrobiology, Chinese Academy of Sciences, Wuhan, Hubei 430072, China. Electronic address:
Article Synopsis
- The Eastern Route of China's South-to-North Water Diversion Project faces potential heavy metal contamination in lakes, prompting a study on ecological risks using advanced machine learning techniques.
- Researchers collected sediment samples from two lakes across different seasons, finding significantly higher heavy metal levels, especially in autumn, with priority pollutants like arsenic and cadmium.
- The study concluded that over 70% of heavy metal pollution is linked to human activities, offering valuable insights for environmental management and pollution mitigation related to water diversion projects.
A Nontoxic and Biocompatible Method for Augmenting Mechanical Strength of Acellular Matrix by Silk Fibroin Impregnation.
ACS Appl Bio Mater
October 2024
Division of In-vivo Models and Testing, Biomedical Technology Wing, Sree Chitra Tirunal Institute for Medical Sciences and Technology, Thiruvananthapuram, Kerala 695012, India.
Biological scaffolds are plagued by poor biomechanical properties and untimely degradation. These limitations have yet to be addressed without compromising their biocompatibility. It is desirable to avoid inflammation and have degradation with concomitant host collagen deposition or even site-appropriate regeneration for the successful outcome of an implanted biological scaffold.
View Article and Find Full Text PDFMapping the cellular expression patterns of vascular endothelial growth factor aa and bb genes and their receptors in the adult zebrafish brain during constitutive and regenerative neurogenesis.
Neural Dev
September 2024
UMR 1188, Diabète Athérothrombose Thérapies Réunion Océan Indien (DéTROI), Université de La Réunion, INSERM, Saint-Pierre, La Réunion, France.
The complex interplay between vascular signaling and neurogenesis in the adult brain remains a subject of intense research. By exploiting the unique advantages of the zebrafish model, in particular the persistent activity of neural stem cells (NSCs) and the remarkable ability to repair brain lesions, we investigated the links between NSCs and cerebral blood vessels. In this study, we first examined the gene expression profiles of vascular endothelial growth factors aa and bb (vegfaa and vegfbb), under physiological and regenerative conditions.
View Article and Find Full Text PDFContributions of the Abductor Muscles to Rotational and Distractive Stability of the Hip in a Biomechanical Cadaveric Model.
Orthop J Sports Med
March 2024
Orthopaedic Biomechanics Laboratory, Cedars-Sinai Medical Center, Los Angeles, California, USA.
Background: The gluteus minimus (GMin) and gluteus medius (GMed) are important dynamic stabilizers of the hip, but quantitative data on their biomechanical roles in stabilizing the hip are currently lacking.
Purpose: To (1) establish a reproducible biomechanical cadaveric model of the hip abductor complex and (2) characterize the effects of loading the GMin and GMed on extraneous femoral rotation and distraction.
Study Design: Controlled laboratory study.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!